INDEX

Explanations

specific variations of the letter "f" or its corresponding sounds 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 @ 23-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L23R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.23.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

Ã²i

-0.18

InBackground

-0.16

aly

-0.15

esson

-0.15

asso

-0.15

ÏĮÎ´

-0.15

Ã³ÅĤ

-0.15

vla

-0.15

acin

-0.14

 tinh

-0.14

POSITIVE LOGITS

ysis

0.18

éĿ

0.17

DP

0.15

éĻ¶

0.15

yg

0.15

0.14

ies

0.14

 Denn

0.14

 competence

0.14

enn

0.14

Activations Density 0.026%

specific variations of the letter "f" or its corresponding sounds in various contexts

No Comments

No Known Activations