INDEX

Explanations

references to terrorist or militant groups

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

 addCriterion

-0.17

veau

-0.17

outil

-0.16

 consect

-0.15

qe

-0.15

è´¨

-0.15

à¤

-0.14

asjon

-0.14

opr

-0.14

esus

-0.14

POSITIVE LOGITS

aho

0.16

arity

0.16

Brun

0.14

da

0.14

 meeting

0.14

aji

0.14

.hs

0.13

ster

0.13

ince

0.13

Activations Density 0.036%

references to terrorist or militant groups

No Comments

No Known Activations