INDEX

Explanations

references to political figures and their actions or decisions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 11-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L11R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.11.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

 Kron

-0.15

_deinit

-0.15

NSIndexPath

-0.15

è°±

-0.14

ãĥ³ãĥĩãĤ£

-0.14

Î¼Î¿Î¯

-0.14

throp

-0.14

ãİ

-0.14

 seper

-0.14

atern

-0.14

POSITIVE LOGITS

assin

0.18

endale

0.15

HIP

0.15

imary

0.15

bum

0.14

brane

0.14

uraa

0.14

 redistrib

0.14

iken

0.14

IBUT

0.14

Activations Density 0.069%

references to political figures and their actions or decisions

No Comments

No Known Activations