INDEX

Explanations

specific numerical values and counts related to various items and categories

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

unas

-0.15

optera

-0.15

umer

-0.15

iaux

-0.14

raud

-0.14

ory

-0.14

ri

-0.14

bjerg

-0.14

ica

-0.14

POSITIVE LOGITS

iÃ¨me

0.19

fold

0.17

-sided

0.17

antry

0.16

-handed

0.15

onta

0.15

/qu

0.15

/if

0.15

orra

0.15

odoxy

0.15

Activations Density 0.205%

specific numerical values and counts related to various items and categories

No Comments

No Known Activations