INDEX

Explanations

references to specific entities, particularly numbers and brands related to coffee

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

-0.15

fts

-0.15

ocab

-0.15

rop

-0.14

 Bian

-0.14

 Paste

-0.14

ekim

-0.14

enberg

-0.13

ynet

-0.13

POSITIVE LOGITS

.AutoScaleMode

0.16

 Mane

0.15

sÄ±

0.15

AILS

0.15

.infinity

0.14

ROM

0.14

elts

0.14

'er

0.14

UED

0.14

etak

0.14

Activations Density 0.223%

references to specific entities, particularly numbers and brands related to coffee

No Comments

No Known Activations