INDEX

Explanations

mentions of various governors

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 2-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L2R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.2.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

Jvm

-0.15

åĿĬ

-0.15

 ((__

-0.14

ursday

-0.14

 Ð±Ð¾Ñı

-0.13

igy

-0.13

appa

-0.13

 Trait

-0.13

æ³Ĭ

-0.13

agg

-0.13

POSITIVE LOGITS

leen

0.16

hood

0.15

hunt

0.15

oven

0.15

orado

0.14

lien

0.14

quito

0.14

stown

0.14

Vision

0.13

 trá»įng

0.13

Activations Density 0.005%

mentions of various governors

No Comments

No Known Activations