INDEX

Explanations

references to leadership and related concepts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 23-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L23R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.23.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

iese

-0.15

pare

-0.15

raw

-0.14

 Estr

-0.14

ble

-0.14

pared

-0.14

©

-0.14

jin

-0.13

 Treasure

-0.13

qing

-0.13

POSITIVE LOGITS

 schema

0.18

schema

0.17

onto

0.17

rdf

0.17

-schema

0.17

 Neutral

0.16

dct

0.16

EntryPoint

0.16

Neutral

0.16

UBY

0.16

Activations Density 0.003%

references to leadership and related concepts

No Comments

No Known Activations