INDEX

Explanations

terms related to emotional experiences or feelings

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 12-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L12R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.12.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

PILE

-0.16

flater

-0.16

ãĥĥãĥĹ

-0.16

/goto

-0.15

anship

-0.15

 addCriterion

-0.15

ÐµÑĢÐ¿

-0.15

.cloudflare

-0.14

ServiceImpl

-0.14

.ToInt

-0.14

POSITIVE LOGITS

 already

0.23

already

0.20

 Already

0.17

uster

0.17

Already

0.17

iner

0.15

icky

0.15

Fay

0.15

Activations Density 0.143%

terms related to emotional experiences or feelings

No Comments

No Known Activations