INDEX

Explanations

affirmative and negative responses or indications related to decisions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 6-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L6R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.6.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

anth

-0.15

agt

-0.15

ssi

-0.15

empo

-0.14

gos

-0.14

ha

-0.14

ØŃÙĩ

-0.14

aine

-0.14

anche

-0.13

andin

-0.13

POSITIVE LOGITS

 stavu

0.15

 Helm

0.14

olini

0.14

ÏīÎ¼Î±

0.14

arem

0.14

VERTISEMENT

0.14

iona

0.14

abella

0.13

Hip

0.13

 timeval

0.13

Activations Density 0.030%

affirmative and negative responses or indications related to decisions

No Comments

No Known Activations