INDEX

Explanations

specific nouns related to medical or health-related terms

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

-0.16

ellant

-0.15

 nail

-0.15

ANGUAGE

-0.15

 nails

-0.15

odal

-0.14

OKEN

-0.14

anki

-0.14

lep

-0.14

oken

-0.13

POSITIVE LOGITS

positor

0.15

aily

0.15

iks

0.14

ìĭ¤

0.14

_UNICODE

0.13

QUIRED

0.13

æ¸¯

0.13

 Shelf

0.13

aris

0.13

ire

0.13

Activations Density 0.303%

specific nouns related to medical or health-related terms

No Comments

No Known Activations