INDEX

Explanations

phrases related to reduction, selection, and narrowing down options

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 12-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L12R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.12.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

cerebras/SlimPajama-627B

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

raj

-0.16

 widest

-0.15

yte

-0.15

ç¹Ķ

-0.14

á»ĩ

-0.14

æ¦ľ

-0.14

ĵĺ

-0.13

TemplateName

-0.13

zab

-0.13

plural

-0.13

POSITIVE LOGITS

HELL

0.17

aters

0.17

 simpl

0.16

 Simpl

0.15

criptor

0.15

erif

0.15

ater

0.15

focus

0.15

erville

0.14

iner

0.14

Activations Density 0.275%

phrases related to reduction, selection, and narrowing down options

No Comments

No Known Activations