INDEX

Explanations

expressions that signify possession or association

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 7-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L7R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.7.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

uru

-0.16

elm

-0.15

obile

-0.14

ibu

-0.14

udi

-0.14

otto

-0.14

resent

-0.14

nic

-0.14

uj

-0.13

foobar

-0.13

POSITIVE LOGITS

lical

0.16

imson

0.15

 Marsh

0.14

 cardinal

0.14

orian

0.14

Rol

0.14

scal

0.14

essional

0.14

 Dillon

0.13

Activations Density 0.027%

expressions that signify possession or association

No Comments

No Known Activations