INDEX

Explanations

geographic locations and names

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

GI

-0.16

otte

-0.15

 Continental

-0.14

 å£

-0.14

otti

-0.14

GV

-0.14

 accom

-0.14

enia

-0.14

osto

-0.14

POSITIVE LOGITS

umat

0.16

_VC

0.15

pora

0.15

anoi

0.15

aoke

0.15

 Ãľl

0.14

isible

0.14

omics

0.14

solete

0.14

omik

0.14

Activations Density 0.041%

geographic locations and names

No Comments

No Known Activations