INDEX

Explanations

specific letters, symbols, and numbers that denote formal or academic content

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 13-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L13R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.13.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

essel

-0.16

nist

-0.16

incinn

-0.15

Å¾

-0.15

headline

-0.15

jur

-0.15

pants

-0.14

/OR

-0.14

 mutate

-0.14

ugu

-0.14

POSITIVE LOGITS

ä½³

0.16

¼åĲĪ

0.15

erman

0.14

fold

0.14

ossier

0.14

aby

0.14

ilda

0.13

ãĥ¼ãĥł

0.13

ouch

0.13

Activations Density 0.259%

specific letters, symbols, and numbers that denote formal or academic content

No Comments

No Known Activations