INDEX

Explanations

references to publishing details, including publishers and locations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 11-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L11R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.11.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

oss

-0.16

hol

-0.15

 Freund

-0.14

 majority

-0.14

ypes

-0.14

 holder

-0.14

 Edwards

-0.14

TM

-0.14

 Branch

-0.14

min

-0.14

POSITIVE LOGITS

ctest

0.16

ilder

0.15

ailable

0.15

-NLS

0.15

LOPT

0.14

 háº¡ng

0.14

ICODE

0.14

 ØªÙĤØ³

0.14

odable

0.14

.glide

0.14

Activations Density 0.026%

references to publishing details, including publishers and locations

No Comments

No Known Activations