INDEX

Explanations

tags or labels that categorize content

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

ByUrl

-0.16

maj

-0.15

erson

-0.15

lover

-0.15

CLOCKS

-0.14

Å¡ka

-0.14

eldig

-0.14

è¬Ŀ

-0.14

Å¡tÃŃ

-0.14

ãĤĴéĸĭ

-0.14

POSITIVE LOGITS

0.17

0.15

 decisions

0.14

JW

0.14

 replace

0.14

_nth

0.14

qus

0.14

iona

0.13

 middle

0.13

Activations Density 0.000%

tags or labels that categorize content

No Comments

No Known Activations