INDEX

Explanations

phrases indicating emotional states or conditions related to personal crises

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 5-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L5R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.5.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

yi

-0.15

ddie

-0.14

ACT

-0.14

*pow

-0.14

yd

-0.14

acia

-0.14

 Pratt

-0.14

iad

-0.14

ACT

-0.14

POSITIVE LOGITS

IZER

0.15

veis

0.15

Ã¢h

0.15

ToProps

0.15

 mÃ¡t

0.14

_cre

0.14

cona

0.14

.cond

0.14

ħn

0.13

izer

0.13

Activations Density 0.042%

phrases indicating emotional states or conditions related to personal crises

No Comments

No Known Activations