INDEX

Explanations

instances of the word "removed" 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

Gad

-0.16

fri

-0.16

-0.15

Ef

-0.14

umb

-0.14

strtolower

-0.14

Pit

-0.14

eff

-0.14

Ãºde

-0.14

ff

-0.13

POSITIVE LOGITS

hazi

0.15

_ctxt

0.15

foot

0.14

awn

0.14

.tc

0.14

malink

0.13

 sana

0.13

WithContext

0.13

phan

0.13

 theano

0.13

Activations Density 0.007%

instances of the word "removed" in various contexts

No Comments

No Known Activations