INDEX

Explanations

variations of the word "depending" 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 @ 15-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L15R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.15.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

opis

-0.16

Î³Î¿Ïģ

-0.16

áº¯t

-0.15

svp

-0.15

panies

-0.15

ses

-0.14

quia

-0.14

ruba

-0.14

dings

-0.14

 bust

-0.14

POSITIVE LOGITS

 whether

0.19

 upon

0.17

<|begin_of_text|>

0.16

 depending

0.15

Ý

0.15

 circumstances

0.15

whether

0.15

ally

0.15

FFT

0.15

avad

0.15

Activations Density 0.012%

variations of the word "depending" in various contexts

No Comments

No Known Activations