INDEX

Explanations

occurrences of phrases indicating openness or availability

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 31-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L31R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.31.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

ARCH

-0.17

 ëĵľë¦½ëĭĪëĭ¤

-0.16

 addCriterion

-0.15

anon

-0.15

Î®ÏĤ

-0.15

 Bonds

-0.15

urma

-0.15

ãĤ¦ãĥĪ

-0.15

 Stark

-0.14

braco

-0.14

POSITIVE LOGITS

 season

0.17

stein

0.17

 Inspector

0.17

 seasonal

0.16

 ÑģÐµÐ·

0.16

 seasons

0.15

 inspector

0.15

morgan

0.15

-season

0.15

 site

0.15

Activations Density 0.005%

occurrences of phrases indicating openness or availability

No Comments

No Known Activations