INDEX

Explanations

announcements about new shows or events

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 7-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L7R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.7.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

inka

-0.16

æľĽ

-0.16

 Conway

-0.15

rc

-0.14

_CONVERT

-0.13

 Ð½Ð°Ð²

-0.13

herent

-0.13

cord

-0.13

ãĥĸãĥ«

-0.13

İ

-0.13

POSITIVE LOGITS

uluk

0.16

Fol

0.16

apo

0.15

ibu

0.15

roid

0.15

ouver

0.14

imd

0.14

ogui

0.14

ogie

0.14

quine

0.14

Activations Density 0.143%

announcements about new shows or events

No Comments

No Known Activations