INDEX

Explanations

instances of the word "hold" in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L1R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.1.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

ANTE

-0.15

ccione

-0.15

rana

-0.15

jÄħ

-0.14

.listBox

-0.14

iphy

-0.14

ikit

-0.14

citation

-0.14

ially

-0.14

Ãºi

-0.14

POSITIVE LOGITS

akes

0.16

ings

0.15

sted

0.15

reds

0.14

back

0.14

 Sullivan

0.14

 frag

0.14

aby

0.14

 onto

0.14

aces

0.14

Activations Density 0.044%

instances of the word "hold" in various contexts

No Comments

No Known Activations