INDEX

Explanations

symbols and formatting used in code or markup languages

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 15-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L15R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.15.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

æ»¿

-0.14

bor

-0.14

Pen

-0.14

Routing

-0.14

 Thrones

-0.14

 pending

-0.14

logan

-0.14

ì²Ļ

-0.14

Nem

-0.14

ort

-0.14

POSITIVE LOGITS

VERSE

0.16

imuth

0.15

 âĨĳ

0.15

ripper

0.15

_budget

0.14

yo

0.14

aliz

0.14

ãĤĩ

0.14

 exhaust

0.14

upal

0.14

Activations Density 0.015%

symbols and formatting used in code or markup languages

No Comments

No Known Activations