INDEX

Explanations

the word "ang" and its contextual implications

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

.spin

-0.16

 èĳ

-0.15

Î¬Î¶

-0.14

à¤¿à¤Ł

-0.14

lon

-0.14

wert

-0.14

mill

-0.13

)::

-0.13

ÐµÑĢÐ¶Ð°Ð²

-0.13

pu

-0.13

POSITIVE LOGITS

 hitch

0.18

ench

0.17

ÐºÐ°Ð²

0.15

aroo

0.15

ando

0.15

ophage

0.15

ouri

0.15

ailable

0.15

older

0.14

ijd

0.14

Activations Density 0.000%

the word "ang" and its contextual implications

No Comments

No Known Activations