INDEX

Explanations

titles of films or shows along with their associated metadata

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

 Ãĸ

-0.16

 BÃ¼

-0.15

 MÃ¼ller

-0.14

 Åł

-0.14

 Å½

-0.14

 GÃ¶

-0.14

 GÃ¼n

-0.14

 Ãľ

-0.13

GÃ¼n

-0.13

 Å¡

-0.13

POSITIVE LOGITS

Æ°ng

0.27

Æ°á»Ŀng

0.27

Æ°Æ¡ng

0.26

inh

0.26

áº±ng

0.25

á»«

0.25

áº¡nh

0.25

áº¯ng

0.25

áº§u

0.25

á»ĳng

0.25

Activations Density 0.031%

titles of films or shows along with their associated metadata

No Comments

No Known Activations