INDEX

Explanations

instances of the word "hang" and its variations in different contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 7-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L7R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.7.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

amped

-0.17

amins

-0.17

erate

-0.15

chin

-0.15

ëª

-0.15

leta

-0.15

ials

-0.14

lez

-0.14

omanip

-0.14

egral

-0.13

POSITIVE LOGITS

 hanging

0.16

ry

0.16

lim

0.15

 hung

0.15

rippling

0.15

Ont

0.15

rier

0.14

olo

0.14

IFA

0.14

 Hang

0.14

Activations Density 0.028%

instances of the word "hang" and its variations in different contexts

No Comments

No Known Activations