INDEX

Explanations

references to transportation and accessibility details

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

imm

-0.17

usher

-0.15

ColumnType

-0.15

elve

-0.14

uba

-0.14

.compiler

-0.14

cott

-0.14

.LoadScene

-0.13

ught

-0.13

Wan

-0.13

POSITIVE LOGITS

 particularly

0.17

 especially

0.17

 particular

0.17

å°¤

0.15

opoulos

0.15

 especialmente

0.15

//{{

0.15

 PARTICULAR

0.15

ovi

0.14

especially

0.14

Activations Density 0.258%

references to transportation and accessibility details

No Comments

No Known Activations