INDEX

Explanations

references to rows and columns in tabular data contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 3-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L3R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.3.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

aly

-0.15

 abrupt

-0.15

zh

-0.14

is

-0.14

 Noel

-0.14

io

-0.14

qq

-0.14

uo

-0.13

POSITIVE LOGITS

slu

0.17

soever

0.17

anford

0.16

Ð¾ÑĩÐ½Ð¾

0.15

poses

0.15

swith

0.15

alley

0.14

ission

0.14

avax

0.14

ostel

0.14

Activations Density 0.029%

references to rows and columns in tabular data contexts

No Comments

No Known Activations