INDEX

Explanations

references to mental health issues and social injustices

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 14-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L14R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.14.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

 semiclass

-0.16

Ìģc

-0.14

¶Į

-0.14

jee

-0.13

oute

-0.13

 Cumhur

-0.13

emachine

-0.13

èĪĪ

-0.13

atures

-0.13

 nonatomic

-0.13

POSITIVE LOGITS

 actual

0.55

actual

0.47

 Actual

0.42

Actual

0.42

 actually

0.42

çľŁæŃ£

0.40

 real

0.38

(actual

0.35

_actual

0.35

 true

0.35

Activations Density 0.250%

references to mental health issues and social injustices

No Comments

No Known Activations