INDEX

Explanations

references to "string" in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 29-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L29R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.29.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

strate

-0.20

_STRING

-0.16

 Ramp

-0.16

 Ð³Ð¾Ð»

-0.15

ror

-0.15

adena

-0.15

_string

-0.15

_STR

-0.15

 strings

-0.15

æ³¡

-0.14

POSITIVE LOGITS

ently

0.38

ency

0.30

yb

0.26

ent

0.26

ed

0.25

encies

0.25

endo

0.25

 quart

0.23

0.22

er

0.22

Activations Density 0.014%

references to "string" in various contexts

No Comments

No Known Activations