INDEX

Explanations

negations or limitations regarding actions or qualities

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 19-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L19R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.19.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

igli

-0.15

ares

-0.15

Vas

-0.14

ili

-0.14

ali

-0.14

chine

-0.13

ombo

-0.13

onga

-0.13

ign

-0.13

itta

-0.13

POSITIVE LOGITS

 newly

0.24

 recently

0.21

recent

0.19

 Newly

0.18

 currently

0.18

Recently

0.18

 henÃ¼z

0.17

å·²

0.17

currently

0.17

 novÄĽ

0.17

Activations Density 0.021%

negations or limitations regarding actions or qualities

No Comments

No Known Activations