INDEX

Explanations

occurrences of the substring "cho" and its variations in different contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 17-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L17R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.17.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

ugin

-0.15

Æ¯á»

-0.15

avers

-0.15

ç½®

-0.14

POOL

-0.14

herits

-0.14

IDGET

-0.14

asto

-0.14

unya

-0.14

roid

-0.14

POSITIVE LOGITS

lift

0.17

ory

0.16

ie

0.16

ester

0.16

 ÐĲÐ½Ð´

0.15

ORMAT

0.15

leaf

0.15

apple

0.15

emy

0.15

emaker

0.15

Activations Density 0.015%

occurrences of the substring "cho" and its variations in different contexts

No Comments

No Known Activations