INDEX

Explanations

references to academic publications and institution names, particularly in mathematics and science contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 12-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L12R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.12.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

aland

-0.20

 Sims

-0.15

oline

-0.15

Imm

-0.15

Byl

-0.15

olis

-0.15

rome

-0.15

á»ī

-0.15

eras

-0.14

 stall

-0.14

POSITIVE LOGITS

 tablesp

0.16

ATED

0.14

 {{--<

0.14

dz

0.14

ated

0.14

_Result

0.14

0.13

ObjectName

0.13

Activations Density 0.052%

references to academic publications and institution names, particularly in mathematics and science contexts

No Comments

No Known Activations