INDEX

Explanations

references to academic degrees and examinations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 17-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L17R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.17.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

ocab

-0.16

éģº

-0.16

esterday

-0.15

plib

-0.15

ahn

-0.14

 Folk

-0.14

jar

-0.14

ander

-0.13

 Fate

-0.13

legg

-0.13

POSITIVE LOGITS

 research

0.17

 Research

0.17

 defended

0.16

ItemClick

0.16

 Leban

0.15

aÄŁa

0.15

acl

0.15

usercontent

0.14

ABD

0.14

hood

0.14

Activations Density 0.025%

references to academic degrees and examinations

No Comments

No Known Activations

references to academic degrees and examinations

No Comments

No Known Activations