INDEX

Explanations

phrases indicating actions and events that take place

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

antom

-0.16

ungs

-0.15

ugs

-0.14

ym

-0.14

-hop

-0.14

 Kraj

-0.14

ug

-0.14

igators

-0.14

Ð´Ð°Ð¼

-0.13

iat

-0.13

POSITIVE LOGITS

/////////////////////////////////////////////////////////////////////////////↵

0.14

 Boulder

0.14

acher

0.14

ãĤ¹ãĤ¯

0.14

achu

0.14

unist

0.14

 å°

0.14

ÏĥÎ¿Î½

0.14

adoo

0.13

 Greene

0.13

Activations Density 0.008%

phrases indicating actions and events that take place

No Comments

No Known Activations