INDEX

Explanations

expressions related to teamwork and collective experience

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 27-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L27R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.27.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

-0.17

 wÅĤa

-0.15

å¯Ĵ

-0.15

 punches

-0.14

NFL

-0.14

 punch

-0.14

 Professional

-0.14

zÄĻ

-0.13

 Punch

-0.13

 proper

-0.13

POSITIVE LOGITS

 district

0.21

 districts

0.18

district

0.18

 Practices

0.17

arsity

0.17

 practices

0.17

istrict

0.17

 sectional

0.16

 vars

0.16

District

0.16

Activations Density 0.040%

expressions related to teamwork and collective experience

No Comments

No Known Activations