INDEX

Explanations

references to specific authors and literary works

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 6-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L6R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.6.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

oom

-0.18

 replic

-0.15

 Pend

-0.15

ke

-0.15

ÛĮÚ©

-0.15

ç»ı

-0.14

isin

-0.14

brick

-0.14

Lad

-0.14

Urb

-0.14

POSITIVE LOGITS

ï»¿#

0.18

_singleton

0.17

ARING

0.17

oled

0.16

rette

0.15

Äįel

0.15

_UNICODE

0.15

Ð¾Ð½Ð¸

0.14

_SHADOW

0.14

ãĤĵãģ©

0.14

Activations Density 0.020%

references to specific authors and literary works

No Comments

No Known Activations