INDEX

Explanations

references to specific characters or principal figures in a narrative

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

ulo

-0.16

BOR

-0.15

 misd

-0.15

 davon

-0.15

exampleInput

-0.14

 poles

-0.14

Ã¼st

-0.14

rouw

-0.14

.annot

-0.14

Ð¾Ð´Ñĸ

-0.14

POSITIVE LOGITS

çĸ

0.16

gn

0.15

essed

0.15

Zem

0.14

oun

0.14

ipy

0.14

 Dunn

0.14

ABCDEFGHI

0.14

.browser

0.13

 dash

0.13

Activations Density 0.041%

references to specific characters or principal figures in a narrative

No Comments

No Known Activations