INDEX

Explanations

phrases related to accountability and public scrutiny of figures in positions of power

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 14-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L14R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.14.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

erot

-0.17

Animate

-0.16

tel

-0.15

hol

-0.15

 Animalia

-0.15

lg

-0.14

Inlining

-0.14

entai

-0.14

ham

-0.14

 Marcos

-0.14

POSITIVE LOGITS

ulet

0.16

 bond

0.15

_ASC

0.14

ÑģÑĤÐ²

0.14

::$

0.14

abee

0.14

_conditions

0.14

Î´ÏģÎ¿

0.13

elocity

0.13

altern

0.13

Activations Density 0.008%

phrases related to accountability and public scrutiny of figures in positions of power

No Comments

No Known Activations