INDEX

Explanations

references to time periods or historical events

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L8R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.8.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

omen

-0.18

ukes

-0.16

arth

-0.15

 breadth

-0.15

peat

-0.15

lex

-0.15

 dÃ³

-0.14

 repeated

-0.14

al

-0.14

atis

-0.14

POSITIVE LOGITS

 Sesso

0.16

edl

0.15

isphere

0.15

Multiplicity

0.15

rame

0.15

SOLE

0.14

HLT

0.14

lavÃŃ

0.14

hlas

0.14

regor

0.14

Activations Density 0.021%

references to time periods or historical events

No Comments

No Known Activations