INDEX

Explanations

expressions of negation or denial

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 20-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L20R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.20.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

ward

-0.19

ulle

-0.17

ged

-0.16

stu

-0.16

ried

-0.14

_UNUSED

-0.14

named

-0.14

cessive

-0.14

airo

-0.14

?q

-0.14

POSITIVE LOGITS

oint

0.18

 longer

0.17

 matter

0.17

 doubt

0.15

 differently

0.15

xious

0.15

obs

0.15

 sooner

0.14

theless

0.14

ScreenWidth

0.14

Activations Density 0.036%

expressions of negation or denial

No Comments

No Known Activations