INDEX

Explanations

references to lesser-known or neglected aspects of history and literature

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 11-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L11R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.11.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

iid

-0.18

 Reporter

-0.15

reds

-0.14

Reporter

-0.14

ê»ĺ

-0.14

ATEST

-0.14

 prevalence

-0.14

aju

-0.13

 Lobby

-0.13

conde

-0.13

POSITIVE LOGITS

 hidden

0.19

oser

0.18

jax

0.16

 side

0.15

chet

0.15

se

0.15

aea

0.15

idon

0.14

 Pear

0.14

 extended

0.14

Activations Density 0.153%

references to lesser-known or neglected aspects of history and literature

No Comments

No Known Activations