INDEX

Explanations

references to web technologies or coding structures

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L1R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.1.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

iece

-0.16

EDA

-0.15

ikat

-0.15

Ã±ana

-0.15

çľł

-0.15

ibling

-0.15

gom

-0.15

 instruct

-0.14

 sibling

-0.14

nun

-0.14

POSITIVE LOGITS

IRROR

0.17

oster

0.15

iem

0.15

indexes

0.15

iro

0.15

0.14

 Pers

0.13

ourn

0.13

DBG

0.13

 Intro

0.13

Activations Density 0.005%

references to web technologies or coding structures

No Comments

No Known Activations