INDEX

Explanations

import statements in code

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

 sinks

-0.17

ded

-0.15

Accessor

-0.15

 sink

-0.14

 profession

-0.14

usions

-0.14

 tier

-0.14

 chore

-0.14

 pedig

-0.14

POSITIVE LOGITS

/random

0.15

INST

0.15

eful

0.14

.cp

0.14

ronic

0.14

 Ð¿Ð¾ÑħÐ¾Ð´

0.14

/std

0.14

 kabil

0.14

iming

0.14

ÐµÐ»Ð°

0.14

Activations Density 0.035%

import statements in code

No Comments

No Known Activations