INDEX

Explanations

specific nouns or terms related to biology, computation, and physical structures

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 15-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L15R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.15.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

ents

-0.17

ittest

-0.15

 ward

-0.15

ORT

-0.15

 Gross

-0.15

dae

-0.14

ToSend

-0.14

eten

-0.14

alice

-0.14

Î³Î¿Ïį

-0.14

POSITIVE LOGITS

 Fold

0.15

antan

0.14

ERVED

0.14

AVED

0.14

fold

0.14

quivos

0.14

Jou

0.14

OKIE

0.14

apos

0.14

Activations Density 0.035%

specific nouns or terms related to biology, computation, and physical structures

No Comments

No Known Activations