INDEX

Explanations

references to proximity or location

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

patible

-0.15

ÑĳÐ»

-0.15

_drv

-0.15

æ¡

-0.14

 migrationBuilder

-0.14

bert

-0.14

gia

-0.14

deo

-0.14

ongan

-0.14

vox

-0.14

POSITIVE LOGITS

{{{

0.17

aland

0.17

 Nicholson

0.15

Ĺ

0.15

icks

0.14

mk

0.14

cis

0.14

eri

0.13

est

0.13

Activations Density 0.002%

references to proximity or location

No Comments

No Known Activations