INDEX

Explanations

references to potential candidates or applicants

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L8R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.8.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

OLA

-0.16

 sort

-0.15

hem

-0.14

ady

-0.14

ola

-0.14

hir

-0.14

áº¯c

-0.14

iola

-0.14

abyrin

-0.14

unker

-0.13

POSITIVE LOGITS

/current

0.18

ideon

0.15

/ws

0.14

ãģ°ãģĭãĤĬ

0.14

æ±

0.14

ideographic

0.13

ograf

0.13

atoes

0.13

Nob

0.13

Activations Density 0.024%

references to potential candidates or applicants

No Comments

No Known Activations