INDEX

Explanations

instances of the word "each" and its variations, indicating a focus on collective experiences or individual instances within a group

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 9-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L9R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.9.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

cerebras/SlimPajama-627B

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

åĪĢ

-0.15

iction

-0.14

 checker

-0.14

../

-0.14

igo

-0.14

hait

-0.14

 tire

-0.14

clusions

-0.13

CHR

-0.13

 rain

-0.13

POSITIVE LOGITS

mvc

0.17

Î¯Î´Î±

0.15

unge

0.15

çĽ®ãģ®

0.15

linger

0.15

dum

0.15

ivant

0.15

Ð¸ÑĤÑĥ

0.14

XD

0.14

 Duffy

0.14

Activations Density 0.034%

instances of the word "each" and its variations, indicating a focus on collective experiences or individual instances within a group

No Comments

No Known Activations