INDEX

Explanations

references to specific individuals or entities in a narrative context

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L1R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.1.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

ÐºÑĢÐ°

-0.15

azen

-0.14

ends

-0.14

esp

-0.14

thing

-0.14

plib

-0.14

ugin

-0.14

mention

-0.14

xon

-0.13

 Feld

-0.13

POSITIVE LOGITS

stras

0.17

chy

0.16

rame

0.15

undle

0.15

alers

0.15

ood

0.15

erk

0.14

ahat

0.14

PHA

0.14

resi

0.14

Activations Density 0.015%

references to specific individuals or entities in a narrative context

No Comments

No Known Activations