INDEX

Explanations

terms related to self-management and mental health awareness

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 2-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L2R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.2.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

serie

-0.17

TK

-0.17

yre

-0.15

aber

-0.15

-0.14

 Bord

-0.14

tk

-0.14

Ã¡ch

-0.14

zeÅĦ

-0.14

 sobie

-0.13

POSITIVE LOGITS

/self

0.20

EDA

0.17

 Self

0.14

rou

0.14

Ð¸Ð²Ð°

0.14

aler

0.14

Æ°á»£ng

0.14

 Partial

0.14

elez

0.14

(simp

0.13

Activations Density 0.028%

terms related to self-management and mental health awareness

No Comments

No Known Activations