INDEX

Explanations

mentions of the "Washington Post" and related publications

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 5-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L5R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.5.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

cerebras/SlimPajama-627B

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

Nat

-0.16

weis

-0.15

 Pawn

-0.15

Pawn

-0.14

launcher

-0.14

OP

-0.14

ucha

-0.14

weit

-0.14

POSITIVE LOGITS

-thumbnails

0.17

 scrim

0.15

_PTR

0.15

.tbl

0.15

loub

0.15

dech

0.15

Ð°Ð½Ñģ

0.14

entin

0.14

ç«

0.14

ateria

0.14

Activations Density 0.005%

mentions of the "Washington Post" and related publications

No Comments

No Known Activations