INDEX

Explanations

numerical values and their 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

aya

-0.16

 VerfÃ¼gung

-0.15

.oracle

-0.15

loit

-0.15

oles

-0.14

ÙĦØŃ

-0.14

erna

-0.14

_ary

-0.14

 eskort

-0.14

icros

-0.14

POSITIVE LOGITS

/+

0.18

unce

0.17

ãĤ

0.16

ought

0.15

.pretty

0.14

uther

0.14

oui

0.14

 Sheridan

0.14

/null

0.13

rends

0.13

Activations Density 0.084%

numerical values and their contexts

No Comments

No Known Activations