INDEX

Explanations

references to family members and relationships

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

ÏģÎ¹Î¬

-0.17

áº©u

-0.16

trfs

-0.15

 addCriterion

-0.15

bach

-0.14

Ð¶Ð½Ð¾

-0.14

ADX

-0.14

landa

-0.14

jerne

-0.14

 './../

-0.13

POSITIVE LOGITS

 Hitch

0.14

Taj

0.14

 Bare

0.14

 Glass

0.14

 cooper

0.14

åį

0.13

 Numbers

0.13

Wit

0.13

 Brow

0.13

Activations Density 0.003%

references to family members and relationships

No Comments

No Known Activations