INDEX

Explanations

locations and geographical features

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 30-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L30R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.30.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

Éµ

-0.17

dzi

-0.17

awy

-0.16

ÙĬÙĪÙĨ

-0.15

 äº¤

-0.15

aso

-0.15

idlo

-0.15

iou

-0.14

oden

-0.14

InSeconds

-0.14

POSITIVE LOGITS

Ste

0.17

ste

0.17

lag

0.16

Ø§ÙĪÙĨØ¯

0.16

Lag

0.16

TERS

0.15

-lib

0.15

 Steam

0.15

stein

0.14

(rel

0.14

Activations Density 0.029%

locations and geographical features

No Comments

No Known Activations