INDEX

Explanations

occurrences of the word "or"

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L1R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.1.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

ediator

-0.16

ema

-0.15

emu

-0.15

es

-0.15

 neutral

-0.15

 auditor

-0.14

sut

-0.14

etter

-0.14

agt

-0.14

egt

-0.14

POSITIVE LOGITS

ycz

0.16

ries

0.16

RIES

0.15

ahl

0.15

 Mature

0.15

cks

0.15

deck

0.15

outil

0.15

ÑģÐ»Ð¸

0.14

atories

0.14

Activations Density 0.050%

occurrences of the word "or"

No Comments

No Known Activations