INDEX

Explanations

occurrences of the word "of" and related expressions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 26-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L26R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.26.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

imore

-0.16

 DataType

-0.15

baugh

-0.15

 Ø°

-0.15

inth

-0.15

removeAttr

-0.15

onth

-0.14

asurement

-0.14

ìķ¡

-0.14

 Kirk

-0.14

POSITIVE LOGITS

ä»ķ

0.17

ewood

0.16

ĭ

0.15

ÑıÑĤ

0.15

iliz

0.15

osite

0.15

.baidu

0.14

iez

0.14

_IOCTL

0.14

 å¯Į

0.14

Activations Density 0.018%

occurrences of the word "of" and related expressions

No Comments

No Known Activations