INDEX

Explanations

references to "candidates" in various contexts, particularly related to nominations or positions

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

coming

-0.17

fully

-0.16

pery

-0.16

azor

-0.16

gow

-0.15

/cgi

-0.15

oya

-0.15

mond

-0.15

ington

-0.15

fld

-0.15

POSITIVE LOGITS

hood

0.17

ifornia

0.16

ç»ıçĲĨ

0.15

hÅ¯

0.15

evice

0.14

apult

0.14

ughter

0.14

êµ°

0.14

vertiser

0.14

mps

0.14

Activations Density 0.020%

references to "candidates" in various contexts, particularly related to nominations or positions

No Comments

No Known Activations