INDEX

Explanations

terms related to operations or functions, particularly those with "With" and various levels of engagement or attachment

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L1R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.1.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

pul

-0.15

elix

-0.15

Pul

-0.14

ormsg

-0.14

 fund

-0.14

HOR

-0.14

Hor

-0.14

atcher

-0.14

estruction

-0.14

roll

-0.13

POSITIVE LOGITS

urette

0.19

alette

0.16

isas

0.15

.readValue

0.15

iston

0.14

oles

0.14

unts

0.14

lÃ½

0.14

isify

0.14

dee

0.14

Activations Density 0.009%

terms related to operations or functions, particularly those with "With" and various levels of engagement or attachment

No Comments

No Known Activations