INDEX

Explanations

repetitive phrases indicating constancy or habitual actions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 28-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L28R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.28.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

 altogether

-0.19

 overall

-0.18

 often

-0.17

overall

-0.17

oft

-0.16

 Overall

-0.16

 stÃ¡le

-0.16

aro

-0.16

pty

-0.15

 immer

-0.15

POSITIVE LOGITS

greens

0.21

ready

0.20

cky

0.20

 been

0.18

green

0.18

-available

0.17

-present

0.17

udes

0.17

ovnÄĽ

0.16

igator

0.16

Activations Density 0.073%

repetitive phrases indicating constancy or habitual actions

No Comments

No Known Activations