INDEX

Explanations

names of people and their titles or affiliations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 10-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L10R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.10.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

endif

-0.17

agnost

-0.15

athe

-0.15

ochrome

-0.15

prox

-0.15

pla

-0.14

Å¾ÃŃ

-0.14

placement

-0.14

elage

-0.14

nod

-0.14

POSITIVE LOGITS

ongan

0.17

 autof

0.15

 knull

0.14

ãĤ·ãĥ§ãĥ³

0.13

LIBINT

0.13

 Permission

0.13

]âĢı

0.13

 Reporter

0.13

iceps

0.13

å¹¹

0.13

Activations Density 0.516%

names of people and their titles or affiliations

No Comments

No Known Activations