INDEX

Explanations

references to academic positions and fields of study

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 10-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L10R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.10.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

iform

-0.16

eyen

-0.16

oma

-0.15

 æĮ

-0.15

ickle

-0.15

pras

-0.14

him

-0.14

uien

-0.14

sov

-0.14

fone

-0.14

POSITIVE LOGITS

rax

0.17

cargo

0.15

itsu

0.14

Alo

0.14

èĹ¤

0.14

 sprink

0.14

éļĨ

0.13

FN

0.13

 Lights

0.13

Activations Density 0.060%

references to academic positions and fields of study

No Comments

No Known Activations