INDEX

Explanations

code-related symbols and syntax, particularly associated with variables and object attributes

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 7-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L7R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.7.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

ovy

-0.16

xbd

-0.15

pll

-0.15

baugh

-0.15

 Classe

-0.14

xcd

-0.14

/octet

-0.14

 Canter

-0.14

xfb

-0.14

ssc

-0.14

POSITIVE LOGITS

ilor

0.17

 Holt

0.15

upo

0.14

oton

0.14

 Moor

0.14

dah

0.14

 Marino

0.14

 Marsh

0.14

opol

0.14

Kil

0.13

Activations Density 0.001%

code-related symbols and syntax, particularly associated with variables and object attributes

No Comments

No Known Activations