INDEX

Explanations

references to prominent political figures and their activities

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

onth

-0.16

onica

-0.16

Writes

-0.15

ÐĶÐļ

-0.15

awan

-0.14

.aspect

-0.14

.documentation

-0.14

ä¹ĭä¸Ģ

-0.14

alÄ±k

-0.13

OWER

-0.13

POSITIVE LOGITS

 foreign

0.14

paque

0.14

il

0.13

preh

0.13

 Foreign

0.13

ereal

0.13

 Tone

0.13

igs

0.13

TR

0.13

cmc

0.13

Activations Density 0.084%

references to prominent political figures and their activities

No Comments

No Known Activations