INDEX

Explanations

code-related syntax and function definitions

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

asic

-0.15

lood

-0.15

inters

-0.14

oid

-0.14

ult

-0.13

omba

-0.13

 winners

-0.13

 spirits

-0.13

 answering

-0.13

POSITIVE LOGITS

 input

0.54

input

0.45

 Input

0.43

 inputs

0.42

_input

0.41

-input

0.41

 INPUT

0.40

Input

0.40

INPUT

0.40

è¾ĵåħ¥

0.39

Activations Density 0.358%

code-related syntax and function definitions

No Comments

No Known Activations