INDEX

Explanations

special characters or symbols that indicate emphasis or negation

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 15-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L15R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.15.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

ichick

-0.16

ieurs

-0.15

ellen

-0.14

ãĤĵ

-0.13

rypto

-0.13

lÃ½

-0.13

preci

-0.13

Fon

-0.13

ainer

-0.13

omid

-0.13

POSITIVE LOGITS

seealso

0.15

 incl

0.14

à¤°à¤£

0.14

/fw

0.14

 Willi

0.13

 sheer

0.13

 READ

0.13

 Wikip

0.13

 disp

0.13

~~~~~~~~~~~~~~~~

0.12

Activations Density 0.118%

special characters or symbols that indicate emphasis or negation

No Comments

No Known Activations