INDEX

Explanations

specific letters and symbols, particularly the letter "A" 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 @ 6-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L6R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.6.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

cape

-0.18

ling

-0.17

ality

-0.17

-0.16

pper

-0.16

na

-0.15

lei

-0.15

ut

-0.15

 haze

-0.15

POSITIVE LOGITS

buquerque

0.20

SEN

0.18

quivos

0.17

bsolute

0.16

ording

0.15

/libs

0.15

ordable

0.15

EUR

0.15

beiter

0.15

umni

0.14

Activations Density 0.228%

specific letters and symbols, particularly the letter "A" in various contexts

No Comments

No Known Activations