INDEX

Explanations

references to specific names or terms associated with individuals or groups

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 17-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L17R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.17.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

ettings

-0.18

keit

-0.17

Ð¸ÑĢÑĥ

-0.16

quence

-0.15

æ¶Ī

-0.15

ÙĪÛĮÙĨ

-0.15

nton

-0.15

hoot

-0.15

lopen

-0.15

rama

-0.14

POSITIVE LOGITS

ertainment

0.24

ucky

0.22

ennial

0.20

ricular

0.19

ally

0.18

ilation

0.18

tir

0.18

eb

0.17

ebb

0.17

Activations Density 0.058%

references to specific names or terms associated with individuals or groups

No Comments

No Known Activations