INDEX

Explanations

formatted sections and metadata typically found in structured documents or citations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 5-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L5R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.5.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

RTL

-0.16

pson

-0.16

peÄį

-0.15

aggio

-0.15

usercontent

-0.15

RPC

-0.14

nist

-0.14

odka

-0.14

fty

-0.14

earer

-0.14

POSITIVE LOGITS

Î³Î·

0.16

ait

0.16

at

0.15

 included

0.15

ather

0.14

ant

0.14

Ã¼f

0.14

 rubber

0.14

dem

0.14

Activations Density 0.232%

formatted sections and metadata typically found in structured documents or citations

No Comments

No Known Activations