INDEX

Explanations

references to locations and locality within the text

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

ager

-0.16

feld

-0.15

 /**<

-0.15

 Lesser

-0.14

å¹ķ

-0.14

olph

-0.14

âĢĮâĢĮ

-0.14

 Oaks

-0.14

thro

-0.14

POSITIVE LOGITS

chio

0.18

ally

0.17

ourt

0.16

zek

0.15

ulong

0.15

harma

0.15

ihar

0.14

 Playboy

0.14

HITE

0.14

nv

0.14

Activations Density 0.015%

references to locations and locality within the text

No Comments

No Known Activations