INDEX

Explanations

mentions of significant historical dates and events

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 6-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L6R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.6.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

cerebras/SlimPajama-627B

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

arts

-0.15

etin

-0.15

.getElementsBy

-0.14

Ø±Ø§Ø¯

-0.14

cq

-0.14

xeb

-0.14

ulse

-0.14

urre

-0.14

prav

-0.14

 ÎłÏģÏī

-0.13

POSITIVE LOGITS

bsites

0.16

Kou

0.16

 last

0.15

 Wolff

0.15

ent

0.15

ml

0.15

lass

0.15

par

0.14

dem

0.14

 concern

0.14

Activations Density 0.161%

mentions of significant historical dates and events

No Comments

No Known Activations