INDEX

Explanations

conditional phrases and decision-making scenarios

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 12-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L12R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.12.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

oor

-0.15

 TRACE

-0.14

heid

-0.14

 Encounter

-0.14

 Edgar

-0.14

 Seeder

-0.14

readcr

-0.13

-regexp

-0.13

 Commit

-0.13

mamak

-0.13

POSITIVE LOGITS

binations

0.15

oca

0.15

zac

0.14

èĥĨ

0.14

eut

0.14

 Wonder

0.13

Ä±f

0.13

avis

0.13

iola

0.13

ateria

0.13

Activations Density 0.134%

conditional phrases and decision-making scenarios

No Comments

No Known Activations