INDEX

Explanations

occurrences of the word "för" 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 @ 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

iny

-0.16

éĿ©

-0.15

getAs

-0.15

ustos

-0.14

prus

-0.14

viso

-0.14

intree

-0.14

otta

-0.14

enburg

-0.14

agini

-0.14

POSITIVE LOGITS

ivi

0.16

ic

0.14

bab

0.14

bang

0.14

bat

0.14

 whether

0.14

ken

0.13

wig

0.13

Kel

0.13

 Tomb

0.13

Activations Density 0.006%

occurrences of the word "för" and its variations in different contexts

No Comments

No Known Activations