INDEX

Explanations

instances of the word "talk" and its variants

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 27-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L27R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.27.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

fold

-0.18

ment

-0.17

uv

-0.16

als

-0.16

conc

-0.15

/full

-0.15

conte

-0.15

 fully

-0.14

ory

-0.14

eenth

-0.14

POSITIVE LOGITS

 shop

0.25

ative

0.24

-shop

0.24

Shop

0.23

shop

0.23

 smack

0.23

-talk

0.21

 Shop

0.21

_shop

0.19

shops

0.19

Activations Density 0.038%

instances of the word "talk" and its variants

No Comments

No Known Activations