INDEX

Explanations

references to the word "blink" and its variations in different contexts

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

inen

-0.15

TRA

-0.15

ë¦½

-0.14

_locals

-0.14

 ë©´

-0.14

Fac

-0.13

 renewal

-0.13

ries

-0.13

 RaisePropertyChanged

-0.13

Lip

-0.13

POSITIVE LOGITS

ervas

0.19

upy

0.17

lej

0.16

erve

0.15

boru

0.15

legate

0.14

ãĥŃãĥ³

0.14

UnitTest

0.14

ingly

0.14

 Threshold

0.14

Activations Density 0.007%

references to the word "blink" and its variations in different contexts

No Comments

No Known Activations