INDEX

Explanations

references to governmental and organizational entities related to state, federal, and international contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 14-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L14R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.14.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

ema

-0.16

-0.14

ubu

-0.14

visor

-0.14

ffe

-0.13

bolt

-0.13

ets

-0.13

 damp

-0.13

UBLE

-0.13

POSITIVE LOGITS

-wide

0.21

 version

0.16

 versions

0.16

 spou

0.16

wide

0.16

kÃ¼

0.15

 Barrett

0.15

-version

0.14

 edition

0.14

Activations Density 0.131%

references to governmental and organizational entities related to state, federal, and international contexts

No Comments

No Known Activations